DDK: Dynamic structure pruning based on differentiable search and recursive knowledge distillation for BERT
Zhou Zhang, Yang Lu, Tengfei Wang, Xing Wei, Zhen Wei, Zhen Wei
Topics & Concepts
Computer sciencePruningBenchmark (surveying)DistillationDifferentiable functionWeightingMachine learningArtificial intelligenceLanguage modelScale (ratio)MathematicsQuantum mechanicsAgronomyPhysicsOrganic chemistryRadiologyChemistryBiologyGeodesyMathematical analysisMedicineGeographyTopic ModelingNatural Language Processing TechniquesAdvanced Neural Network Applications